SwarmOS Demonstrated at Idea Festival 142
PacoCheezdom writes "Intelligent Life has short summary of a demonstration by MIT professor James McLurkin of his new group-minded robots, which run an operating system called 'Swarm OS'. The robots are able to work together as a group not by communicating with all members of the group at once, but by talking only to their neighbors, and model other similar behaviors performed by bees and ants. "
Re:My experience (Score:2, Informative)
More on research with videos (Score:3, Informative)
James McLurkin (Score:5, Informative)
All the robots have a sound system, though; the first thing Mr. McLurkin did during his presentation was to have a single robot request that 6 other robots follow it, and the swarm picked and allocated 6 robots, and they all went off in a chain, singing "Hi-ho, hi-ho, it's off to work we go".
Check out James McLurkin's website for some presentations and videos:
http://people.csail.mit.edu/jamesm/ [mit.edu]
Obligatory mirror-link (Score:2, Informative)
Re:I think they need a bigger Swarm for their serv (Score:3, Informative)
Here [64.233.167.104] is the Google cache if anyone is interested.
Article Text (Score:5, Informative)
In his second dispatch from the Idea Festival in Louisville, Evgeny Morozov watches a podium-full of robots buzz around like bees, ask each other questions, find an orange, leave the room, form an orchestra, and prepare one day to save your life
Re:My experience (Score:2, Informative)
Re:Practical application: self-laying mines (Score:4, Informative)
Too late! DARPA already has a project for a "self-healing" minefield based on a very similar approach.
Re:My experience (Score:3, Informative)
There is also immense military interest. Research doesn't get done on a large scale without funding. Funding, generally speaking - at least in engineering, doesn't come without someone with some influence being convinced that there will be applications.
Emergence & real world applications (Score:3, Informative)
No, it isn't.
Swarm intelligence relies on emergence that arises from many simple agents that interact locally with each other (i.e. without a master controller), using minimal rules. These are the keypoints of this field: there isn't a single point of failure, you can ensure degradation of service gracefully, you can even perform self-repair, etc. It allows to solve large problems without having to implement a complex monolithic system.
Naturally, the difficulties then lie in defining the right rules for the swarm of agents to generate the expected macroscopic group behaviour.
I know of at least one shipping company (in Switzerland IIRC) that uses swarm intelligence techniques to give a good solution to the TSP in reasonable time, and uses that to schedule the plan for its trucks daily. More applications are being developed, including small robots to inspect parts in inaccessible locations (e.g. airplane), etc.